A Web-Based Automated Image Processing Research Platform for Cochlear Implantation-Related Studies.

The robust delineation of the cochlea and its inner structures combined with the detection of the electrode of a cochlear implant within these structures is essential for envisaging a safer, more individualized, routine image-guided cochlear implant therapy. We present Nautilus-a web-based research platform for automated pre- and post-implantation cochlear analysis. Nautilus delineates cochlear structures from pre-operative clinical CT images by combining deep learning and Bayesian inference approaches. It enables the extraction of electrode locations from a post-operative CT image using convolutional neural networks and geometrical inference. By fusing pre- and post-operative images, Nautilus is able to provide a set of personalized pre- and post-operative metrics that can serve the exploration of clinically relevant questions in cochlear implantation therapy. In addition, Nautilus embeds a self-assessment module providing a confidence rating on the outputs of its pipeline. We present a detailed accuracy and robustness analyses of the tool on a carefully designed dataset. The results of these analyses provide legitimate grounds for envisaging the implementation of image-guided cochlear implant practices into routine clinical workflows.

Paediatric motor phenotypes in early-onset ataxia, developmental coordination disorder, and central hypotonia.

AIMS: To investigate the accuracy of phenotypic early-onset ataxia (EOA) recognition among developmental conditions, including developmental coordination disorder (DCD) and hypotonia of central nervous system origin, and the effect of scientifically validated EOA features on changing phenotypic consensus. METHOD: We included 32 children (4-17y) diagnosed with EOA (n=11), DCD (n=10), and central hypotonia (n=11). Three paediatric neurologists independently assessed videotaped motor behaviour phenotypically and quantitatively (using the Scale for Assessment and Rating of Ataxia [SARA]). We determined: (1) phenotypic interobserver agreement and phenotypic homogeneity (percentage of phenotypes with full consensus by all three observers according to the underlying diagnosis); (2) SARA (sub)score profiles; and (3) the effect of three scientifically validated EOA features on phenotypic consensus. RESULTS: Phenotypic homogeneity occurred in 8 out of 11, 2 out of 10, and 1 out of 11 patients with EOA, DCD, and central hypotonia respectively. Homogeneous phenotypic discrimination of EOA from DCD and central hypotonia occurred in 16 out of 21 and 22 out of 22 patients respectively. Inhomogeneously discriminated EOA and DCD phenotypes (5 out of 21) revealed overlapping SARA scores with different SARA subscore profiles. After phenotypic reassessment with scientifically validated EOA features, phenotypic homogeneity changed from 16 to 18 patients. INTERPRETATION: In contrast to complete distinction between EOA and central hypotonia, the paediatric motor phenotype did not reliably distinguish between EOA and DCD. Reassessment with scientifically validated EOA features could contribute to a higher phenotypic consensus. Early-onset ataxia (EOA) and central hypotonia motor phenotypes were reliably distinguished. EOA and developmental coordination disorder (DCD) motor phenotypes were not reliably distinguished. The EOA and DCD phenotypes have different profiles of the Scale for Assessment and Rating of Ataxia.

FENOTIPOS PEDIÁTRICOS MOTORES EN ATAXIA DE INICIO TEMPRANO, TRASTORNO DEL DESARROLLO DE LA COORDINACIÓN E HIPOTONÍA DE ORIGEN CENTRAL: OBJETIVOS: Investigar la precisión del reconocimiento fenotípico de ataxia de inicio temprano (EOA) con respecto a trastornos del desarrollo, incluido el trastorno del desarrollo de la coordinación (TDC) y la hipotonía de origen central. Investigar el efecto de las características científicamente validadas de EOA sobre el consenso fenotípico entre los evaluadores. MÉTODO: Se incluyeron 32 niños (4-17 años) diagnosticados con EOA (n = 11), TDC (n = 10) e hipotonía central (n = 11). Tres neurólogos pediátricos evaluaron de forma independiente el comportamiento motor grabado en video en cuanto a las características fenotípica y cuantitativa (utilizando la Escala de evaluación y calificación de la ataxia [SARA]). Determinamos: (1) coincidencia fenotípica entre los observadores y homogeneidad fenotípica (porcentaje de fenotipos con consenso total de los tres observadores según el diagnóstico subyacente), (2) perfiles de (sub)puntajes en el SARA y (3) el efecto sobre el consenso fenotípico de tres características de EOA validadas científicamente. RESULTADOS: La homogeneidad fenotípica ocurrió en 8 de 11, 2 de 10 y 1 de 11 pacientes con EOA, DCD e hipotonía central, respectivamente. La discriminación fenotípica homogénea de EOA con respecto a TDC e hipotonía central se produjo en 16 de 21 y 22 de 22 pacientes, respectivamente. Los fenotipos EOA y TDC que no fueron discriminados de manera homogénea por los observadores (5 de 21) revelaron superposición en los puntajes del SARA con diferentes perfiles en los subpuntajes del SARA. Después de una reevaluación fenotípica con características EOA científicamente validadas, la homogeneidad fenotípica cambió de 16 a 18 pacientes. INTERPRETACIÓN: En contraste con la distinción completa entre EOA e hipotonía central, el fenotipo motor pediátrico no distinguió confiablemente entre EOA y TDC. La evaluación en base a características EOA científicamente validadas podría contribuir a un mayor consenso fenotípico.

FENÓTIPOS MOTORES PEDIÁTRICOS NA ATAXIA DE INÍCIO PRECOCE, TRANSTORNO DO DESENVOLVIMENTO DA COORDENACÃO, E HIPOTONIA CENTRAL: OBJETIVOS: Investigar a acurácia do reconhecimento fenotípico da ataxia de início precoce (AIP) entre condições desenvolvimentais, incluindo o transtorno do desenvolvimento da coordenação (TDC) e a hipotonia de origem no sistema nervoso central, e o efeito de aspectos cientificamente validados da AIP na modificação do consenso fenotípico. MÉTODO: Incluímos 32 crianças (4-17a) diagnosticadas com AIP (n=11), TDC (n=10), e hipotonia central (n=11). Três neurologistas pediátricos avaliaram de maneira independente por meio de vídeo o comportamento motor tanto por meio do fenótiopo quanto quantitativamente (usando a Escala para Avaliação e Pontuação da Ataxia) [EAPA]). Determinamos: (1) a concordânica fenotípica inter-observadores e a homogeneidade fenotípica (porcentagem de fenótipos com consenso completo pelos três observadores de acordo com o diagnóstico de base, (2) perfis segundo os (sub)escores da EAPA, e (3) o efeito de três aspectos cientificamente validados da AIP sobre o consenso fenotípico. RESULTADOS: A homogeneidade fenotípica ocorreu em 8 entre 12, 2 entre 10, e 1 entre 11 pacientes com AIP, TDC, e hipotonia central, respectivamente. A discriminação fenotípica homogênea da AIP com relação ao TDC e hipotonia central ocorreu em 16 entre 21 e 21 entre 22 pacientes, respectivamente. A discriminação não homogêna dos fenótipos AIP e TDC (5 em 21) revelou escores da EAPA que sobrepõem com diferentes perfis de subescores da EAPA. Após reavaliação fenotípica com aspectos cientificamente validados da AIP, a homogeneidade fenotípica mudou de 16 para 18 pacientes. INTERPRETAÇÃO: Em contraste com a completa distinção entre AIP e hipotonia central, o fenótipo motor pediátrico não distinguiu confiavelmente entre AIP e TDC. A reavaliação com aspectos cientificamente valiaddos da AIP pode contribuir para um maior consenso fenotípica. contrast to complete distinction between EOA and central hypotonia, the paediatric motor phenotype did not reliably distinguish between EOA and DCD. eassessment with scientifically validated EOA features could contribute to a higher phenotypic consensus.

Machine learning in the integration of simple variables for identifying patients with myocardial ischemia.

BACKGROUND: A significant number of variables are obtained when characterizing patients suspected with myocardial ischemia or at risk of MACE. Guidelines typically use a handful of them to support further workup or therapeutic decisions. However, it is likely that the numerous available predictors maintain intrinsic complex interrelations. Machine learning (ML) offers the possibility to elucidate complex patterns within data to optimize individual patient classification. We evaluated the feasibility and performance of ML in utilizing simple accessible clinical and functional variables for the identification of patients with ischemia or an elevated risk of MACE as determined through quantitative PET myocardial perfusion reserve (MPR). METHODS: 1,234 patients referred to Nitrogen-13 ammonia PET were analyzed. Demographic (4), clinical (8), and functional variables (9) were retrieved and input into a cross-validated ML workflow consisting of feature selection and modeling. Two PET-defined outcome variables were operationalized: (1) any myocardial ischemia (regional MPR < 2.0) and (2) an elevated risk of MACE (global MPR < 2.0). ROC curves were used to evaluate ML performance. RESULTS: 16 features were included for boosted ensemble ML. ML achieved an AUC of 0.72 and 0.71 in identifying patients with myocardial ischemia and with an elevated risk of MACE, respectively. ML performance was superior to logistic regression when the latter used the ESC guidelines risk models variables for both PET-defined labels (P < .001 and P = .01, respectively). CONCLUSIONS: ML is feasible and applicable in the evaluation and utilization of simple and accessible predictors for the identification of patients who will present myocardial ischemia and an elevated risk of MACE in quantitative PET imaging.

Distinguishing Patients With a Coordination Disorder From Healthy Controls Using Local Features of Movement Trajectories During the Finger-to-Nose Test.

Assessment of coordination disorders is valuable for monitoring progression of patients, distinguishing healthy and pathological conditions, and ultimately aiding in clinical decision making, thereby offering the possibility to improve medical care or rehabilitation. A common method to assess movement disorders is by using clinical rating scales. However, rating scales depend on the evaluation and interpretation of an observer, implying that subjective phenotypic assignment precedes the application of the scales. Objective and more accurate methods are under continuous development but gold standards are still scarce. Here, we show how a method we previously developed, originally aimed at assessing dynamic balance by a probabilistic generalized linear model, can be used to assess a broader range of functional movements. In this paper, the method is applied to distinguish patients with coordination disorders from healthy controls. We focused on movements recorded during the finger-to-nose task (FNT), which is commonly used to assess coordination disorders. We also compared clinical FNT scores and model scores. Our method achieved 84% classification accuracy in distinguishing patients and healthy participants, using only two features. Future work could entail testing the reliability of the method by using additional features and other clinical tests such as finger chasing, quiet standing, and/or usage of tracking devices such as depth cameras or force plates.

Automatic classification of gait in children with early-onset ataxia or developmental coordination disorder and controls using inertial sensors.

Early-Onset Ataxia (EOA) and Developmental Coordination Disorder (DCD) are two conditions that affect coordination in children. Phenotypic identification of impaired coordination plays an important role in their diagnosis. Gait is one of the tests included in rating scales that can be used to assess motor coordination. A practical problem is that the resemblance between EOA and DCD symptoms can hamper their diagnosis. In this study we employed inertial sensors and a supervised classifier to obtain an automatic classification of the condition of participants. Data from shank and waist mounted inertial measurement units were used to extract features during gait in children diagnosed with EOA or DCD and age-matched controls. We defined a set of features from the recorded signals and we obtained the optimal features for classification using a backward sequential approach. We correctly classified 80.0%, 85.7%, and 70.0% of the control, DCD and EOA children, respectively. Overall, the automatic classifier correctly classified 78.4% of the participants, which is slightly better than the phenotypic assessment of gait by two pediatric neurologists (73.0%). These results demonstrate that automatic classification employing signals from inertial sensors obtained during gait maybe used as a support tool in the differential diagnosis of EOA and DCD. Furthermore, future extension of the classifier's test domains may help to further improve the diagnostic accuracy of pediatric coordination impairment. In this sense, this study may provide a first step towards incorporating a clinically objective and viable biomarker for identification of EOA and DCD.

Tremor Detection Using Parametric and Non-Parametric Spectral Estimation Methods: A Comparison with Clinical Assessment.

In the clinic, tremor is diagnosed during a time-limited process in which patients are observed and the characteristics of tremor are visually assessed. For some tremor disorders, a more detailed analysis of these characteristics is needed. Accelerometry and electromyography can be used to obtain a better insight into tremor. Typically, routine clinical assessment of accelerometry and electromyography data involves visual inspection by clinicians and occasionally computational analysis to obtain objective characteristics of tremor. However, for some tremor disorders these characteristics may be different during daily activity. This variability in presentation between the clinic and daily life makes a differential diagnosis more difficult. A long-term recording of tremor by accelerometry and/or electromyography in the home environment could help to give a better insight into the tremor disorder. However, an evaluation of such recordings using routine clinical standards would take too much time. We evaluated a range of techniques that automatically detect tremor segments in accelerometer data, as accelerometer data is more easily obtained in the home environment than electromyography data. Time can be saved if clinicians only have to evaluate the tremor characteristics of segments that have been automatically detected in longer daily activity recordings. We tested four non-parametric methods and five parametric methods on clinical accelerometer data from 14 patients with different tremor disorders. The consensus between two clinicians regarding the presence or absence of tremor on 3943 segments of accelerometer data was employed as reference. The nine methods were tested against this reference to identify their optimal parameters. Non-parametric methods generally performed better than parametric methods on our dataset when optimal parameters were used. However, one parametric method, employing the high frequency content of the tremor bandwidth under consideration (High Freq) performed similarly to non-parametric methods, but had the highest recall values, suggesting that this method could be employed for automatic tremor detection.